Beschreibung
This book constitutes the proceedings of the 37th European Conference on IR Research, ECIR 2015, held in Vienna, Austria, in March/April 2015. The 44 full papers, 41 poster papers and 7 demonstrations presented together with 3 keynotes in this volume were carefully reviewed and selected from 305 submissions. The focus of the papers were on following topics: aggregated search and diversity, classification, cross-lingual and discourse, efficiency, evaluation, event mining and summarisation, information extraction, recommender systems, semantic and graph-based models, sentiment and opinion, social media, specific search tasks, temporal models and features, topic and document models, user behavior and reproducible IR.
Autorenporträt
InhaltsangabeKeynotes.- Still Haven't Found What I'm Looking For: Suggestions for Search Research.- Mining and Modeling Online Health Search.- What to do if you know everything? Studying human behavior in a virtual world.- Aggregated Search and Diversity.- Towards Query Level Resource Weighting For Diversified Query Expansion.- Exploring Composite Retrieval from the Users' Perspective.- Improving Aggregated Search Coherence.- On-topic Cover Stories from News Archives.- Classification.- Multi-Emotion Detection in User-Generated Reviews.- Classification of historical notary acts with noisy labels.- ConceptFusion: A Flexible Scene Classification Framework.- An Audio-Visual Approach to Music Genre Classiffcation through Affective Color Features.- Cross-Lingual and Discourse.- Multi-Modal Correlated Centroid Space for Multi-Lingual Cross-Modal Retrieval.- A Discourse Search Engine based on Rhetorical Structure Theory.- Knowledge-based Representation for Transductive Multilingual Document Classiffcation.- Distributional Correspondence Indexing for Cross-Language Text Categorization.- Effciency Adaptive Caching of Fresh Web Search Results.- Approximating Weighted Hamming Distance by Probabilistic Selection for Multiple Hash Table.- Graph Regularised Hashing.- Approximate Nearest-Neighbour Search with Inverted Signature Slice Lists.- Evaluation.- A Discriminative Approach to Predicting Assessor Accuracy.- WHOSE A Tool for Whole-Session Analysis in IIR.- Looking for Books in Social Media: An Analysis of Complex Search Requests.- How do Gain and Discount Functions Affect the Correlation between DCG and User Satisfaction?.- Different Rankers on Different Subcollections.- Retrievability Bias: A Comparison of Inequality Measures.- Judging Relevance Using Magnitude Estimation.- Event Mining and Summarisation.- Retrieving Time from Scanned Books.- A Noise-Filtering Approach for Spatio-Temporal Event Detection in Social Media.- Timeline Summarization from Relevant Headlines.- Information Extraction.- A Self-Training CRF Method for Recognizing Product Model Mentions in Web Forums.- Information Extraction Grammars.- Target-based Topic Model for Problem Phrase Extraction.- On Identifying Phrases Using Collection Statistics.- MIST: Top-k Approximate Sub-String Mining using Triplet Statistical Significance.- Recommender Systems.- Active Learning applied to Rating Elicitation for Incentive Purposes.- Entity-Centric Stream Filtering and ranking: Filtering and Unfilterable Documents.- Generating Music Playlists with Hierarchical Clustering and Q-Learning.- Time-sensitive Collaborative Filtering through Adaptive Matrix Completion.- Toward the New Item Problem: Context-enhanced Event Recommendation in Event-based Social Networks.- On the Infence of User Characteristics on Music Recommendation Algorithms.- A Study of Smoothing Methods for Relevance-Based Language Modelling of Recommender Systems.- The Power of Contextual Suggestion.- Semantic and Graph-Based Models.- Exploiting Semantic Annotations for Domain-Specific Entity Search.- Reachability Analysis of Graph Modelled Collections.- Main Core Retention on Graph-of-words for Single-Document Keyword Extraction.- Entity Linking for Web Search Queries.- Sentiment and Opinion.- Beyond Sentiment Analysis: Mining Defects and Improvements from Customer Feedback.- Measuring User Infuence, Susceptibility and Cynicalness in Sentiment Diffusion.- Automated Controversy Detection on the Web.- Learning Sentiment Based Ranked-Lexicons for Opinion Retrieval.- Topic-dependent sentiment classification on Twitter.- Learning Higher-Level Features with Convolutional Restricted Boltzmann Machines for Sentiment Analysis.- Social Media.- Towards Deep Semantic Analysis of Hashtags.- Chalk and Cheese in Twitter: Discriminating Personal and Organization Accounts.- Handling Topic Drift for Topic Tracking in Microblogs.- Detecting Location-centric Communities using Social-Spatial Links with Temporal Constraints.- Using Subjectivity Analysis
Herstellerkennzeichnung:
Springer Verlag GmbH
Tiergartenstr. 17
69121 Heidelberg
DE
E-Mail: juergen.hartmann@springer.com
